AI agents call search_provider_templates to retrieve information from Nango without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries information about available Nango provider templates to help users find templates before integration creation. It performs a read-only search operation without modifying, executing, or deleting any data. No reversible or irreversible changes occur, and no code execution or financial transactions are involved.
From the tool's definition Tool name is 'search_provider_templates' and description states it 'Search[es] Nango provider templates before creating an integration.' The verb 'search' indicates a query operation with no side effects.
Attacks that exploit this kind of access
Search Nango provider templates before creating an integration. It is categorised as a Read tool in the Nango MCP Server, which means it retrieves data without modifying state.
Register the Nango MCP server in PolicyLayer and add a rule for search_provider_templates: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nango. Nothing to install.
search_provider_templates is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_provider_templates rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for search_provider_templates. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
search_provider_templates is provided by the Nango MCP server (levsky22/nango-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →